List your company

Mathematical Reasoning on AMC 2023 (Avg@K Metrics)

86.75Avg@32PPPO
55.737263.788671.8479.8914Dec 4, 2025Dec 6, 2025Dec 8, 2025Dec 10, 2025Dec 12, 2025Dec 14, 2025Dec 17, 2025

Evaluation results

MethodLinks
PPPOBackbone=Qwen3-8B, Evaluation Protocol=zero-shot, avg@322025.1286.75——
DAPO-FTBackbone=Qwen3-8B, Evaluation Protocol=zero-shot, avg@322025.1284.11——
DAPOBackbone=Qwen3-8B, Evaluation Protocol=zero-shot, avg@322025.1283.96——
PPPOBackbone=Qwen3-4B, Evaluation Protocol=zero-shot, avg@322025.1283.06——
DAPO-FTBackbone=Qwen3-4B, Evaluation Protocol=zero-shot, avg@322025.1282——
DAPOBackbone=Qwen3-4B, Evaluation Protocol=zero-shot, avg@322025.1281.63——
GRPOBackbone=Qwen3-8B, Evaluation Protocol=zero-shot, avg@322025.1279.44——
INTUITORBackbone=Qwen3-8B, Evaluation Protocol=zero-shot, avg@322025.1278.24——
GRPOBackbone=Qwen3-4B, Evaluation Protocol=zero-shot, avg@322025.1276.77——
INTUITORBackbone=Qwen3-4B, Evaluation Protocol=zero-shot, avg@322025.1275.83——
Qwen3-8BBackbone=Qwen3-8B, Evaluation Protocol=zero-shot, avg@322025.1275.08——
Qwen3-4BBackbone=Qwen3-4B, Evaluation Protocol=zero-shot, avg@322025.1272.67——
SENTBackbone=DeepSeek-R1-Distill-Qwen-1.5B2025.127071.5670.16
w/ MaskBackbone=DeepSeek-R1-Distill-Qwen-1.5B2025.1269.617068.28
w/ EnBackbone=DeepSeek-R1-Distill-Qwen-1.5B2025.1265.4765.6263.75
w/ ClipBackbone=DeepSeek-R1-Distill-Qwen-1.5B2025.1265.2364.4967.03
w/ High EnBackbone=DeepSeek-R1-Distill-Qwen-1.5B2025.1264.696062.97
w/ CovBackbone=DeepSeek-R1-Distill-Qwen-1.5B2025.1264.3860.9465.94
DAPOBackbone=Qwen3-1.7B, Evaluation Protocol=zero-shot, avg@322025.1263.03——
PPPOBackbone=Qwen3-1.7B, Evaluation Protocol=zero-shot, avg@322025.1262.89——
DAPO-FTBackbone=Qwen3-1.7B, Evaluation Protocol=zero-shot, avg@322025.1262.8——
INTUITORBackbone=Qwen3-1.7B, Evaluation Protocol=zero-shot, avg@322025.1260.99——
GRPOBackbone=Qwen3-1.7B, Evaluation Protocol=zero-shot, avg@322025.1260.24——
GRPOBackbone=DeepSeek-R1-Distill-Qwen-1.5B2025.1258.1256.2560.47
w/ AdvBackbone=DeepSeek-R1-Distill-Qwen-1.5B2025.1258.1260.3156.41
Base modelBackbone=DeepSeek-R1-Distill-Qwen-1.5B2025.1257.5857.8157.03
Qwen3-1.7BBackbone=Qwen3-1.7B, Evaluation Protocol=zero-shot, avg@322025.1256.93——
CISPOModel=Qwen3-14B-Base2026.02——89.84
CISPOModel=Qwen3-30B-A3B-Base (MoE)2026.02——87.03
CISPOModel=Qwen3-8B-Base2026.02——80.94
DAPOModel=Qwen3-14B-Base2026.02——87.66
DAPOModel=Qwen3-30B-A3B-Base (MoE)2026.02——83.75
DAPOModel=Qwen3-8B-Base2026.02——80.94
DISPOModel=Qwen3-14B-Base2026.02——92.03
DISPOModel=Qwen3-30B-A3B-Base (MoE)2026.02——89.38
DISPOModel=Qwen3-8B-Base2026.02——87.66
Starting checkpointModel=Qwen3-14B-Base2026.02——22.19
Starting checkpointModel=Qwen3-30B-A3B-Base (MoE)2026.02——12.5
Starting checkpointModel=Qwen3-8B-Base2026.02——24.69